Neuro-Fuzzy Networks

Considering jointly damage sensitive features (DSFs) of signals recorded by multiple sensors, applying advanced transformations to these DSFs and assessing systematically their contribution to damage detectability and localisation can significantly enhance the performance of structural health monitoring systems. This philosophy is explored here for partial autocorrelation coefficients (PACCs) of acceleration responses. They are interrogated with the help of the linear discriminant analysis based on the Fukunaga-Koontz transformation using datasets of the healthy and selected reference damage states. Then, a simple but efficient fast forward selection procedure is applied to rank the DSF components with respect to statistical distance measures specialised for either damage detection or localisation. For the damage detection task, the optimal feature subsets are identified based on the statistical hypothesis testing. For damage localisation, a hierarchical neuro-fuzzy tool is developed that uses the DSF ranking to establish its own optimal architecture. The proposed approaches are evaluated experimentally on data from non-destructively simulated damage in a laboratory scale wind turbine blade. The results support our claim of being able to enhance damage detectability and localisation performance by transforming and optimally selecting DSFs. It is demonstrated that the optimally selected PACCs from multiple sensors or their Fukunaga-Koontz transformed versions can not only improve the detectability of damage via statistical hypothesis testing but also increase the accuracy of damage localisation when used as inputs into a hierarchical neuro-fuzzy network. Furthermore, the computational effort of employing these advanced soft computing models for damage localisation can be significantly reduced by using transformed DSFs.

A neuro-fuzzy network predictive approach is
introduced to design a control system for nonlinear industrial
process. While the nonlinear process is modeled by neuro-fuzzy
technique containing local CARMA model, traditional
generalized minimum variance predictive control method can be
extended to nonlinear case in a neuro-fuzzy fashion. Boiler steam temperature process is chosen as realistic system for the
demonstration of the techniques discussed and the neuro-fuzzy
controller was found to provide a satisfactory performance over
the complex system.

ABSTRACT

This article discusses issues related to problems encountered on electrical energy measurement due to harmonics distortions in the network. Such distortions may be able to cause considerable errors and consequently an undue amount of energy collection by the supplier. In view of this problem, the objective of this article is to make the process of measuring more efficient electricity through concepts related to Artificial Neural Networks and Neuro-Fuzzy Networks.

RESUMO

Este artigo aborda assuntos relacionados aos problemas encontrados na medição de energia elétrica em decorrência de distorções harmônicas da rede. Tais distorções podem ser capazes de provocar erros consideráveis, acarretando, consequentemente, em cobrança de uma quantidade indevida de energia pela empresa fornecedora. Tendo em vista esse problema, o objetivo deste artigo consiste em tornar o processo de medição de energia elétrica mais eficiente por meio de conceitos referentes a Redes Neurais Artificias e Redes Neuro-Fuzzy. Palavras-chave: Medição de energia elétrica. Distorções Harmônicas. Redes Neurais Artificiais. Redes Neuro-Fuzzy.